can1357 811cb77c52 feat(coding-agent): updated steering interjection format to system notice ...

- Restructured the user interjection prompt to use a system-notice envelope instead of nested message tags.
- Updated associated tests to verify the new system-notice formatting for steering messages.

2026-07-27 17:06:40 +02:00

..

advisor

fix(advisor): reduce stale advisories via delta coalescing, WIP markers, and delivery annotation

2026-07-11 18:56:04 +02:00

agents

feat(coding-agent): added support for task-agent field and model resolution

2026-07-15 00:50:55 +02:00

bench

chore: update changelogs

2026-07-24 02:38:32 +02:00

goals

Merge PR #4927: feat(coding-agent): rewrite /guided-goal interviewer for loop engineering (@metaphorics)

2026-07-23 11:37:14 +02:00

memories

feat(coding-agent): support the local memory backend in the learn tool

2026-06-14 12:03:13 +09:00

skills

chore: reformat

2026-07-01 23:14:36 +02:00

steering

feat(coding-agent): updated steering interjection format to system notice

2026-07-27 17:06:40 +02:00

system

Merge PR #6670: fix(mcp): map mounted tools to xd routes (@jeffscottward)

2026-07-27 04:58:27 +02:00

tools

feat(coding-agent/task): added task.enableEffort setting to gate effort parameter

2026-07-27 07:01:09 +02:00

bench.md

feat(prompt): standardized tool instruction and communication flow

2026-06-29 06:51:13 +02:00

ci-green-request.md

docs(prompts): standardized RFC keywords across prompt surface

2026-06-10 02:07:30 +02:00

dry-balance-bench.md

feat(dry-balance): added live bench mode for OAuth accounts

2026-06-05 11:41:07 +02:00

review-custom-request.md

feat(coding-agent): reworked subagent yields for incremental results

2026-06-28 07:27:01 +02:00

review-headless-request.md

prompts: undo experiment, update system

2026-06-04 17:41:10 +02:00

review-request.md

feat(coding-agent): reworked subagent yields for incremental results

2026-06-28 07:27:01 +02:00